facebookresearch/AugLy
data augmentations for audio, image, text, and video
View on index · View in 3D Map
Related repos
- video and image watermarking code for training and inference
- segment anything in images and videos with sam2
- Library for video understanding research
- turns audio into realistic talking avatars
- Reconstructs 3D scenes from 1000+ images in one forward pass
- Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- AudioCraft: code for generating music, sound effects, and audio compression from raw audio and textinputs
- tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
- Environment for training agents to use apps
